VideoProduct and app demo videoIntermediateGenerates a video

App install ad: 3-second hook opening

Only the opening three seconds of an install ad: a relatable problem moment designed to stop the scroll, to be followed by real app footage.

For: Paid social marketers, Creative strategists, Brand and content marketers · Works with: Google video models (Gemini Omni Flash, Veo 3.1), Runway (Gen-4.5 and earlier), Kling, Any text-to-video or image-to-video tool

Public beta. This prompt was drafted with AI assistance and checked by automated rules, but it has not been reviewed or tested by a person yet. Treat it as a starting point and check the output. It is hidden from search engines while in beta. Use the “Was this prompt useful?” box to tell us what works.

Your prompt

Create a 3-4 second 9:16 opening clip for a mobile app install ad about a bill-splitting app for housemates, aimed at young renters sharing flats. Moment: three housemates stare at a crumpled pile of receipts on a table, each pointing at a different one: a single, instantly relatable problem moment shown through action, with no explanation. Framing: close medium shot from table height, subject large in frame, immediate action from the very first frame (no fade-in, no establishing shot). Camera: quick push-in. Light: bright kitchen light; Look: punchy, saturated, slightly comedic, high contrast so it holds attention in a fast scroll. Sound: overlapping murmurs and a paper-rustle sound. Constraints: no on-screen text, no app logos, no readable UI; this clip is followed by real app footage added in an editor.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

What the app does.

Who it is for.

Placement.

The relatable problem.

Framing.

Camera move.

Light.

Look.

Audio.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

A 3-second opening: three housemates point at different receipts on a messy table with an immediate push-in, no fade-in.

Expected format: A very short opening clip; cut to real app footage after it.

How to use it

  1. Generate several different hook moments and test them against each other.
  2. Follow with real screen recordings.
  3. Keep the opening honest to what the app actually solves.

Limitations

  • A strong hook does not fix a weak offer or product.
  • Install-ad policies differ by network; check them.

Platform notes

Google video models (Gemini Omni Flash, Veo 3.1)

Official docs read · checked 2026-10-11

Google's Gemini API docs describe Veo 3.1 as generating video with native audio, and name Gemini Omni Flash as the recommended default; check current limits for duration and resolution, which the docs page did not list.

General notes on Google video models (Gemini Omni Flash, Veo 3.1)
  • Google's Gemini API docs name Gemini Omni Flash as the recommended default and Veo 3.1 for native audio, video extension and first/last-frame control.
  • Google's detailed Veo prompt guide could not be fully read, so structure here follows general video-prompt anatomy, not Veo-specific claims.

Runway (Gen-4.5 and earlier)

Official docs only partly readable · checked 2026-10-11

Per Runway's help center (seen via search snippet), with image-to-video the image is the first frame, so describe the motion rather than the scene.

General notes on Runway (Gen-4.5 and earlier)
  • Per Runway's help center (seen via search snippet), Gen-4.5 supports text-to-video and image-to-video. With image-to-video the image is the first frame, so describe the motion instead of re-describing the image.

Kling

Not verified: third-party guidance only · checked 2026-10-11

Only third-party guidance was found for Kling: name the camera move explicitly and give the motion an end point. Treat as unverified and test.

General notes on Kling
  • Only third-party guidance was found. Reported advice: name the camera move explicitly, keep the element count modest, and give motion an end point. Model versions behave differently, so test.

Any text-to-video or image-to-video tool

Official docs only partly readable · checked 2026-10-11

Plain scene description that any text-to-video tool can use. OpenAI shut down Sora 2 and its Videos API on 2026-09-24, so no prompt here targets Sora.

General notes on Any text-to-video or image-to-video tool
  • Written as plain scene descriptions: subject, action over time, camera, lighting, style, aspect ratio. Duration, resolution and aspect ratio are usually settings in the tool, not words in the prompt.
  • OpenAI shut down Sora 2 and its Videos API on 2026-09-24, so none of these prompts target Sora.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID vid-015. We will correct or remove it.

Related prompts

  • VideoIntermediateWrites a set of prompts

    10 video hook ideas for one offer (text, not video)

    Generates ten distinct opening lines and first-shot ideas across different hook types, with each hook tied to a testable hypothesis.

    Any capable chat model (ChatGPT, Claude, Gemini, others)

  • VideoIntermediateGenerates a video

    First 3 seconds: visual hook clip

    Generates only the opening shot of a video: a single striking visual designed to stop the scroll, with motion from frame one.

    Google video models (Gemini Omni Flash, Veo 3.1) · Runway (Gen-4.5 and earlier) · Kling +2

  • VideoIntermediateGenerates a video

    App feature highlight b-roll (person with phone)

    People using a phone in context, with an unreadable or blank screen, to be intercut with real app screen recordings.

    Google video models (Gemini Omni Flash, Veo 3.1) · Runway (Gen-4.5 and earlier) · Kling +2

  • VideoIntermediateGenerates a video

    Software feature b-roll (abstract, not a UI replica)

    Atmospheric b-roll that conveys a software capability metaphorically, to cut around your real screen recordings. It never tries to generate readable UI.

    Google video models (Gemini Omni Flash, Veo 3.1) · Runway (Gen-4.5 and earlier) · Kling +2